Towards a Natural Perspective of Smart Homes for Practical Security and Safety Analyses

Towards a Natural Perspective of Smart Homes for Practical Security and Safety Analyses
复制标题

DOI:
10.1109/sp40000.2020.00062
复制
发表时间:
2020-05
期刊:
2020 IEEE Symposium on Security and Privacy (SP)
影响因子:
--
通讯作者:
Sunil Manandhar;Kevin Moran;Kaushal Kafle;Ruhao Tang;D. Poshyvanyk;Adwait Nadkarni
Sunil Manandhar;Kevin Moran;Kaushal Kafle;Ruhao Tang;D. Poshyvanyk;Adwait Nadkarni
中科院分区:
其他
文献类型:
--
作者:
Sunil Manandhar;Kevin Moran;Kaushal Kafle;Ruhao Tang;D. Poshyvanyk;Adwait Nadkarni

文献摘要

被引文献

相似文献

如果不了解实际的家庭使用情况,为智能家居设计实用的安全系统是一项挑战。本文介绍了 Hεlion 的设计和实现,该框架通过识别用户驱动的家庭自动化序列中的规律来生成自然的家庭自动化场景,而这些序列又是根据最终用户创建的例程生成的。我们的关键假设是,用户创建的智能家居事件序列表现出固有的语义模式或自然性,可以对其进行建模并用于生成有效且有用的场景。为了评估我们的方法,我们首先通过从 40 个用户收集的 273 个例程构建的包含 30,518 个家庭自动化事件的语料库,凭经验证明这种自然性假设成立。然后,我们通过 16 名外部评估者进行的两项研究证明,Hεlion 生成的场景对于最终用户来说似乎是有效的。我们通过解决策略规范的挑战,并使用 Hεlion 以最小的努力生成 17 个安全策略,进一步证明了 Hεlion 场景的有用性。我们从结果中提炼出 16 个关键发现,这些发现展示了我们方法的优势、家庭自动化的令人惊讶的方面,以及这个快速发展领域的挑战和机遇。
Designing practical security systems for the smart home is challenging without the knowledge of realistic home usage. This paper describes the design and implementation of Hεlion, a framework that generates natural home automation scenarios by identifying the regularities in user-driven home automation sequences, which are in turn generated from routines created by end-users. Our key hypothesis is that smart home event sequences created by users exhibit inherent semantic patterns, or naturalness that can be modeled and used to generate valid and useful scenarios. To evaluate our approach, we first empirically demonstrate that this naturalness hypothesis holds, with a corpus of 30,518 home automation events, constructed from 273 routines collected from 40 users. We then demonstrate that the scenarios generated by Hεlion seem valid to end-users, through two studies with 16 external evaluators. We further demonstrate the usefulness of Hεlion’s scenarios by addressing the challenge of policy specification, and using Hεlion to generate 17 security/safety policies with minimal effort. We distill 16 key findings from our results that demonstrate the strengths of our approach, surprising aspects of home automation, as well as challenges and opportunities in this rapidly growing domain.